Published March 28, 2022 | Version v1
Conference paper Open

The Importance of Character-Level Information in an Event Detection Model

  • 1. University of La Rochelle, L3i, F-17000, La Rochelle, France
  • 2. Universit´e Paris-Saclay, CEA
  • 3. Universite Paris-Saclay, CEA
  • 4. Universite Paris-Saclay, CNRS, LIMSI, ENSIIE, F-91405, Orsay, France


This paper tackles the task of event detection that aims at identifying and categorizing event mentions in texts. One of the difficulties of this task is the problem of event mentions corresponding to misspelled, custom, or out-of-vocabulary words. To analyze the impact of character-level features, we propose to integrate character embeddings, that can capture morphological and shape information about words, to a convolutional model for event detection. More precisely, we evaluate two strategies for performing such integration and show that a late fusion approach outperforms both an early fusion approach and models integrating character or subword information such as ELMo or BERT.


NLDB_2021_The_Importance_of_Character-Level_Information_in_an_Event_Detection_Model (1).pdf

Additional details


EMBEDDIA – Cross-Lingual Embeddings for Less-Represented Languages in European News Media 825153
European Commission